AI forecasts help WFP make more of its shrinking food assessment data

WFP's Office of Evaluation found that AI tools built with Google Research Africa to forecast household food consumption weeks ahead helped WFP use its reduced assessment data.

  • 2 for an organization

    The evaluation found that the tools helped WFP make more effective use of assessment data that funding cuts had reduced.

  • Not rated society

    The evaluation says that the tools can enable earlier crisis response, and it reports no response that came earlier.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent evaluation report supports the benefit.

The system’s part
Not isolated. The evaluation calls the tools AI-driven and gives no model details, so it does not show that they learn from data. It reports no accuracy figures and does not compare WFP's analysis with and without the tools.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Knowledge Discovery
System
AI-driven tools for forecasting household food consumption several weeks in advance (not named)
Made by
World Food Programme (WFP) with Google Research Africa
Used by
World Food Programme (WFP), for food security analysis
Where
Global (WFP operations, countries not named)
Stage
In routine use
Date
, when the source was published
Kind
Benefit created
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information, Analyzing Data or Information
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Evaluation report, by authors with no tie to the system.

    WFP Office of Evaluation. Strategic evaluation of WFP's adaptation to the evolving partnership landscape. Centralized evaluation report OEV/2025/016, August 2026. Conducted by an external evaluation team between October 2025 and June 2026.

    WFP's partnership with Google Research Africa enhanced WFP's analytical capabilities, including the development of AI-driven tools for forecasting household food consumption several weeks in advance. The tools have helped WFP to make more effective use of assessment data, which are more limited because of funding cuts, and can therefore enable earlier crisis response.

Details

AI system

Workflow

WFP partnered with Google Research Africa to strengthen its analytical capabilities. The partnership developed AI-driven tools that forecast household food consumption several weeks in advance. WFP used the tools to make more of its assessment data.

Follow-up

Conditions for replication

WFP must keep collecting some assessment data, which funding cuts have reduced. Partners must bring capabilities that WFP cannot develop internally.

Entry details

Sector

Humanitarian food security analysis.

Purpose

WFP and Google Research Africa built the tools to forecast household food consumption several weeks in advance.

31 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). AI forecasts help WFP make more of its shrinking food assessment data (AIBD-1166). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1166.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions